Abstract | ||
---|---|---|
Sequential recommendation aims to predict a user's next behavior in near future by using the user's most recent behaviors. Most of the existing methods always embed a user or an item as a point in a vector space, and then model the user's recent behaviors as a sequence with a strict order to generate recommendations. However, both the point representation and strict order rule limit the capacity of sequential recommendation models as the diversity and uncertainty of a user's interests. In this paper, by relaxing the condition that a sequence must follow a strict order, we introduce the box embedding into the sequential recommendation and present a novel model called Box4Rec. Box4Rec embeds a user and the user's historical items as boxes instead of points to model the user's general preference and short-term preference, and then integrates the conjunction and disjunction operations on items to generate flexible recommendation strategies. Experiments on five real-world datasets show the proposed Box4Rec model outperforms the state-of-the-art methods consistently. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1007/978-3-030-75765-6_43 | ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2021, PT II |
Keywords | DocType | Volume |
Flexible order, Box embedding, Sequential recommendation | Conference | 12713 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kai Deng | 1 | 0 | 0.34 |
Jiajin Huang | 2 | 69 | 15.70 |
Jin Qin | 3 | 0 | 1.35 |